© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7842
    Prev
    Next
    INDEX
    Explanations

    existing or already in place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    尤为
    -0.10
    è´¿
    -0.10
    OperationException
    -0.09
    èĩªèIJ¥
    -0.09
    pirit
    -0.09
    ноÑģÑĤей
    -0.09
    ither
    -0.09
    èį¤
    -0.09
    ighter
    -0.08
    å°¤åħ¶
    -0.08
    POSITIVE LOGITS
    çĹĽ
    0.10
    éĥ¨åĪĨåĨħ容
    0.10
    _counters
    0.08
    大海
    0.08
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.08
    èµł
    0.08
    (pa
    0.08
    bane
    0.08
    好æ¶Īæģ¯
    0.08
    è¿ĽåĮĸ
    0.07
    Activations Density 0.030%

    No Known Activations